danosethrus/Hakim

TEXT GENERATIONConcurrency Cost:1Model Size:3.1BQuant:BF16Ctx Length:32kTool Calling:SupportedPublished:Jul 2, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

Hakim is a 3.1 billion parameter instruction-tuned causal language model developed by Daniel Aschalew, based on the Qwen2.5 architecture. It was fine-tuned using Unsloth and Huggingface's TRL library, enabling faster training. This model is designed for general instruction-following tasks, leveraging its efficient fine-tuning process.

Loading preview...

Overview

danosethrus/Hakim is a 3.1 billion parameter instruction-tuned language model developed by Daniel Aschalew. It is built upon the Qwen2.5 architecture and was fine-tuned using the Unsloth library, which is known for accelerating the training process, alongside Huggingface's TRL library.

Key Characteristics

  • Base Model: Qwen2.5-3B-Instruct
  • Parameter Count: 3.1 billion
  • Context Length: 32768 tokens
  • Training Efficiency: Fine-tuned with Unsloth for 2x faster training.
  • License: Apache-2.0, allowing for broad use and distribution.

Potential Use Cases

  • Instruction Following: Designed to respond to a wide range of instructions due to its instruction-tuned nature.
  • Rapid Prototyping: Its efficient training methodology suggests it could be a good candidate for developers looking to quickly fine-tune models for specific tasks.
  • General Language Tasks: Suitable for various natural language processing applications where a 3.1B parameter model is appropriate.